1 files changed, 74 insertions, 85 deletions

diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index ba7af2eca755..27d1a5b7f571 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -29,6 +29,7 @@
 #include <asm/idtentry.h>
 #include <asm/desc.h>
 #include <asm/cpu.h>
+#include <asm/apic.h>
 #include <asm/io_apic.h>
 
 #include <xen/interface/xen.h>
@@ -55,14 +56,15 @@ static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 };
 static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 };
 
 static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
-void asm_cpu_bringup_and_idle(void);
 
 static void cpu_bringup(void)
 {
 	int cpu;
 
 	cr4_init();
+	cpuhp_ap_sync_alive();
 	cpu_init();
+	fpu__init_cpu();
 	touch_softlockup_watchdog();
 
 	/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
@@ -72,7 +74,6 @@ static void cpu_bringup(void)
 	}
 	cpu = smp_processor_id();
 	smp_store_cpu_info(cpu);
-	cpu_data(cpu).x86_max_cores = 1;
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();
@@ -83,7 +84,7 @@ static void cpu_bringup(void)
 
 	set_cpu_online(cpu, true);
 
-	cpu_set_state_online(cpu);  /* Implies full memory barrier. */
+	smp_mb();
 
 	/* We can take interrupts now: we're officially "up". */
 	local_irq_enable();
@@ -97,18 +98,18 @@ asmlinkage __visible void cpu_bringup_and_idle(void)
 
 void xen_smp_intr_free_pv(unsigned int cpu)
 {
+	kfree(per_cpu(xen_irq_work, cpu).name);
+	per_cpu(xen_irq_work, cpu).name = NULL;
 	if (per_cpu(xen_irq_work, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
 		per_cpu(xen_irq_work, cpu).irq = -1;
-		kfree(per_cpu(xen_irq_work, cpu).name);
-		per_cpu(xen_irq_work, cpu).name = NULL;
 	}
 
+	kfree(per_cpu(xen_pmu_irq, cpu).name);
+	per_cpu(xen_pmu_irq, cpu).name = NULL;
 	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
 		per_cpu(xen_pmu_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_pmu_irq, cpu).name);
-		per_cpu(xen_pmu_irq, cpu).name = NULL;
 	}
 }
 
@@ -118,6 +119,7 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	char *callfunc_name, *pmu_name;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
+	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
 				    cpu,
 				    xen_irq_work_interrupt,
@@ -127,10 +129,10 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_irq_work, cpu).irq = rc;
-	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 
 	if (is_xen_pmu) {
 		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
+		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
 		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
 					     xen_pmu_irq_handler,
 					     IRQF_PERCPU|IRQF_NOBALANCING,
@@ -138,7 +140,6 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 		if (rc < 0)
 			goto fail;
 		per_cpu(xen_pmu_irq, cpu).irq = rc;
-		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
 	}
 
 	return 0;
@@ -148,40 +149,18 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	return rc;
 }
 
-static void __init _get_smp_config(unsigned int early)
+static void __init xen_pv_smp_config(void)
 {
-	int i, rc;
-	unsigned int subtract = 0;
-
-	if (early)
-		return;
-
-	num_processors = 0;
-	disabled_cpus = 0;
-	for (i = 0; i < nr_cpu_ids; i++) {
-		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
-		if (rc >= 0) {
-			num_processors++;
-			set_cpu_possible(i, true);
-		} else {
-			set_cpu_possible(i, false);
-			set_cpu_present(i, false);
-			subtract++;
-		}
-	}
-#ifdef CONFIG_HOTPLUG_CPU
-	/* This is akin to using 'nr_cpus' on the Linux command line.
-	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
-	 * have up to X, while nr_cpu_ids is greater than X. This
-	 * normally is not a problem, except when CPU hotplugging
-	 * is involved and then there might be more than X CPUs
-	 * in the guest - which will not work as there is no
-	 * hypercall to expand the max number of VCPUs an already
-	 * running guest has. So cap it up to X. */
-	if (subtract)
-		nr_cpu_ids = nr_cpu_ids - subtract;
-#endif
+	u32 apicid = 0;
+	int i;
+
+	topology_register_boot_apic(apicid++);
 
+	for (i = 1; i < nr_cpu_ids; i++)
+		topology_register_apic(apicid++, CPU_ACPIID_INVALID, true);
+
+	/* Pretend to be a proper enumerated system */
+	smp_found_config = 1;
 }
 
 static void __init xen_pv_smp_prepare_boot_cpu(void)
@@ -209,7 +188,7 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned cpu;
 
-	if (skip_ioapic_setup) {
+	if (ioapic_is_disabled) {
 		char *m = (max_cpus == 0) ?
 			"The nosmp parameter is incompatible with Xen; " \
 			"use Xen dom0_max_vcpus=1 parameter" :
@@ -222,8 +201,6 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 
 	smp_prepare_cpus_common();
 
-	cpu_data(0).x86_max_cores = 1;
-
 	speculative_store_bypass_ht_init();
 
 	xen_pmu_init(0);
@@ -254,15 +231,12 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	struct desc_struct *gdt;
 	unsigned long gdt_mfn;
 
-	/* used to tell cpu_init() that it can proceed with initialization */
-	cpumask_set_cpu(cpu, cpu_callout_mask);
 	if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
 		return 0;
 
 	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
 	if (ctxt == NULL) {
 		cpumask_clear_cpu(cpu, xen_cpu_initialized_map);
-		cpumask_clear_cpu(cpu, cpu_callout_mask);
 		return -ENOMEM;
 	}
 
@@ -316,7 +290,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	return 0;
 }
 
-static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
+static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
 {
 	int rc;
 
@@ -326,14 +300,6 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	xen_setup_runstate_info(cpu);
 
-	/*
-	 * PV VCPUs are always successfully taken down (see 'while' loop
-	 * in xen_cpu_die()), so -EBUSY is an error.
-	 */
-	rc = cpu_check_up_prepare(cpu);
-	if (rc)
-		return rc;
-
 	/* make sure interrupts start blocked */
 	per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
 
@@ -343,15 +309,20 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	xen_pmu_init(cpu);
 
-	rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL);
-	BUG_ON(rc);
-
-	while (cpu_report_state(cpu) != CPU_ONLINE)
-		HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
+	/*
+	 * Why is this a BUG? If the hypercall fails then everything can be
+	 * rolled back, no?
+	 */
+	BUG_ON(HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL));
 
 	return 0;
 }
 
+static void xen_pv_poll_sync_state(void)
+{
+	HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 static int xen_pv_cpu_disable(void)
 {
@@ -367,35 +338,26 @@ static int xen_pv_cpu_disable(void)
 
 static void xen_pv_cpu_die(unsigned int cpu)
 {
-	while (HYPERVISOR_vcpu_op(VCPUOP_is_up,
-				  xen_vcpu_nr(cpu), NULL)) {
+	while (HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu), NULL)) {
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule_timeout(HZ/10);
 	}
+}
 
-	if (common_cpu_die(cpu) == 0) {
-		xen_smp_intr_free(cpu);
-		xen_uninit_lock_cpu(cpu);
-		xen_teardown_timer(cpu);
-		xen_pmu_finish(cpu);
-	}
+static void xen_pv_cleanup_dead_cpu(unsigned int cpu)
+{
+	xen_smp_intr_free(cpu);
+	xen_uninit_lock_cpu(cpu);
+	xen_teardown_timer(cpu);
+	xen_pmu_finish(cpu);
 }
 
-static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */
+static void __noreturn xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */
 {
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);
-	cpu_bringup();
-	/*
-	 * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
-	 * clears certain data that the cpu_idle loop (which called us
-	 * and that we return from) expects. The only way to get that
-	 * data back is to call:
-	 */
-	tick_nohz_idle_enter();
-	tick_nohz_idle_stop_tick_protected();
-
-	cpuhp_online_idle(CPUHP_AP_ONLINE_IDLE);
+	xen_cpu_bringup_again((unsigned long)task_pt_regs(current));
+	BUG();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */
@@ -409,7 +371,12 @@ static void xen_pv_cpu_die(unsigned int cpu)
 	BUG();
 }
 
-static void xen_pv_play_dead(void)
+static void xen_pv_cleanup_dead_cpu(unsigned int cpu)
+{
+	BUG();
+}
+
+static void __noreturn xen_pv_play_dead(void)
 {
 	BUG();
 }
@@ -442,13 +409,29 @@ static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+void __init xen_smp_count_cpus(void)
+{
+	unsigned int cpus;
+
+	for (cpus = 0; cpus < nr_cpu_ids; cpus++) {
+		if (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpus, NULL) < 0)
+			break;
+	}
+
+	pr_info("Xen PV: Detected %u vCPUS\n", cpus);
+	if (cpus < nr_cpu_ids)
+		set_nr_cpu_ids(cpus);
+}
+
 static const struct smp_ops xen_smp_ops __initconst = {
 	.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = xen_pv_smp_prepare_cpus,
 	.smp_cpus_done = xen_smp_cpus_done,
 
-	.cpu_up = xen_pv_cpu_up,
+	.kick_ap_alive = xen_pv_kick_ap,
 	.cpu_die = xen_pv_cpu_die,
+	.cleanup_dead_cpu = xen_pv_cleanup_dead_cpu,
+	.poll_sync_state = xen_pv_poll_sync_state,
 	.cpu_disable = xen_pv_cpu_disable,
 	.play_dead = xen_pv_play_dead,
 
@@ -464,6 +447,12 @@ void __init xen_smp_init(void)
 	smp_ops = xen_smp_ops;
 
 	/* Avoid searching for BIOS MP tables */
-	x86_init.mpparse.find_smp_config = x86_init_noop;
-	x86_init.mpparse.get_smp_config = _get_smp_config;
+	x86_init.mpparse.find_mptable		= x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg	= x86_init_noop;
+
+	/* XEN/PV Dom0 has halfways sane topology information via CPUID/MADT */
+	if (xen_initial_domain())
+		x86_init.mpparse.parse_smp_cfg	= x86_init_noop;
+	else
+		x86_init.mpparse.parse_smp_cfg	= xen_pv_smp_config;
 }